English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Homophily describes the phenomenon that similarity breeds connection, i.e.,individuals tend to form ties with other people who are similar to themselvesin some aspect(s). The similarity in music taste can undoubtedly influence whowe make friends with and shape our social circles. In this paper, we studyhomophily in an online music platform Last.fm regarding user preferencestowards listening to mainstream (M), novel (N), or diverse (D) content.Furthermore, we draw comparisons with homophily based on listening profilesderived from artists users have listened to in the past, i.e., artist profiles.Finally, we explore the utility of users' artist profiles as well as featuresdescribing M, N, and D for the task of link prediction. Our study reveals that:(i) users with a friendship connection share similar music taste based on theirartist profiles; (ii) on average, a measure of how diverse is the music twousers listen to is a stronger predictor of friendship than measures of theirpreferences towards mainstream or novel content, i.e., homophily is strongerfor D than for M and N; (iii) some user groups such as high-novelty-seekers(explorers) exhibit strong homophily, but lower than average artist profilesimilarity; (iv) using M, N and D achieves comparable results on linkprediction accuracy compared with using artist profiles, but the combination offeatures yields the best accuracy results, and (v) using combined features doesnot add value if graph-based features such as common neighbors are available,making M, N, and D features primarily useful in a cold-start userrecommendation setting for users with few friendship connections. The insightsfrom this study will inform future work on social context-aware musicrecommendation, user modeling, and link prediction.

My friends also prefer diverse music: homophily and link prediction with user preferences for mainstream, novelty, and diversity in music